As the field of explainable AI (XAI) is maturing, calls for interactive explanations for (the outputs of) AI models are growing, but the state-of-the-art predominantly focuses on static explanations. In this paper, we focus instead on interactive explanations framed as conflict resolution between agents (i.e. AI models and/or humans) by leveraging on computational argumentation. Specifically, we define Argumentative eXchanges (AXs) for dynamically sharing, in multi-agent systems, information harboured in individual agents' quantitative bipolar argumentation frameworks towards resolving conflicts amongst the agents. We then deploy AXs in the XAI setting in which a machine and a human interact about the machine's predictions. We identify and assess several theoretical properties characterising AXs that are suitable for XAI. Finally, we instantiate AXs for XAI by defining various agent behaviours, e.g. capturing counterfactual patterns of reasoning in machines and highlighting the effects of cognitive biases in humans. We show experimentally (in a simulated environment) the comparative advantages of these behaviours in terms of conflict resolution, and show that the strongest argument may not always be the most effective.
Towards Robust Argumentative Essay Understanding via TIDE: An Interactive Framework with Trial and Debate
School of Computer Science and Technology, East China Normal University(东华师范大学计算机科学与技术学院);Shanghai Institute of Artificial Intelligence for Education, East China Normal University(上海教育人工智能研究院);Lab of Artificial Intelligence for Education, East China Normal University(教育人工智能实验室)
KC-Bench: A Dynamic Interactive Benchmark for Evaluating Knowledge Conflicts in LLM Agents
Shanghai Artificial Intelligence Laboratory(上海人工智能实验室);The University of Hong Kong(香港大学);Xiamen University Malaysia(马来西亚厦门大学);Beijing University of Posts and Telecommunications(北京邮电大学)
P4P: Conflict-Aware Motion Prediction for Planning in Autonomous Driving
Tsinghua University(清华大学);Shanghai Qi Zhi Institute(上海期智研究院);Massachusetts Institute of Technology(麻省理工学院)
运动预测对于在交互式场景中实现自动驾驶车辆的安全运动规划至关重要。它允许规划者识别与其他交通代理的潜在冲突并生成安全的计划。现有的运动预测器通常专注于减少预测误差,但它们如何帮助规划器识别冲突仍然是一个悬而未决的问题。在本文中,我们通过新的冲突相关的指标,如识别冲突的成功率,评估国家的最先进的预测。令人惊讶的是,预测遭受低成功率,从而导致很大比例的碰撞时,我们在一个交互式模拟器中测试的预测规划系统。为了填补这一空白,我们提出了一个简单但有效的替代方案,它结合了基于物理的轨迹生成器和基于学习的关系预测器来识别冲突并推断冲突关系。我们证明了我们的预测器P4P在Waymo Open Motion Dataset的现实交互式驾驶场景中比现有的基于学习的预测器具有更好的性能。
ClawForge: Generating Executable Interactive Benchmarks for Command-Line Agents
University of North Carolina at Chapel Hill(北卡罗来纳大学切里波因特分校);Stanford University(斯坦福大学);University of California, Berkeley(加州大学伯克利分校);University of Southern California(南加州大学);University of California, Santa Cruz(加州大学圣克鲁兹分校)
A Conflicts-free, Speed-lossless KAN-based Reinforcement Learning Decision System for Interactive Driving in Roundabouts
James Watt School of Engineering, University of Glasgow(格拉斯哥大学詹姆斯·瓦特工程学院);Faculty of Science, University of Amsterdam(阿姆斯特丹大学科学学院);School of Computer and Mathematical Sciences, The University of Adelaide(阿德莱德大学计算机与数学科学学院);University of Michigan-Shanghai Jiao Tong University Joint Institute, Shanghai Jiao Tong University(密歇根大学-上海交通大学联合研究所,上海交通大学);School of Electrical and Electronic Engineering, University College Dublin(都柏林大学学院电子与电气工程学院)
Can LLM Agents Stick to the Script? A Benchmark for Long-Horizon Consistency in Interactive Narratives
University of Macau(澳门大学);Westlake University(西湖大学);Harbin Institute of Technology(哈尔滨工业大学);University of Cambridge(剑桥大学);University of Aberdeen(阿伯丁大学)
Finding Counterfactual Explanations through Constraint Relaxations
SFI Centre for Research Training in AI(SFI人工智能研究培训中心);Insight Centre for Data Analytics(Insight数据分析中心);Confirm Centre for Smart Manufacturing(Confirm智能制造中心);University College Cork(科克大学学院)